Search Results for author:
Found 13 papers, 1 papers with code
An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR
In the present paper, an attempt is made to combine Mask-CTC and the triggered attention mechanism to construct a streaming end-to-end automatic speech recognition (ASR) system that provides high performance with low latency.
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
In this work, to promote the word-level representation learning in end-to-end ASR, we propose a hierarchical conditional model that is based on connectionist temporal classification (CTC).
Exploiting Narrative Context and A Priori Knowledge of Categories in Textual Emotion Classification
Recognition of the mental state of a human character in text is a major challenge in natural language processing.
Sentiment Analysis for Emotional Speech Synthesis in a News Dialogue System
As smart speakers and conversational robots become ubiquitous, the demand for expressive speech synthesis has increased.
Improved Mask-CTC for Non-Autoregressive End-to-End ASR
While Mask-CTC achieves remarkably fast inference speed, its recognition performance falls behind that of conventional autoregressive (AR) systems.
Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict
In this work, Mask CTC model is trained using a Transformer encoder-decoder with joint training of mask prediction and CTC.
Audio and Speech Processing Sound
Word Attribute Prediction Enhanced by Lexical Entailment Tasks
Human semantic knowledge about concepts acquired through perceptual inputs and daily experiences can be expressed as a bundle of attributes.
Towards Answer-unaware Conversational Question Generation
Conversational question generation is a novel area of NLP research which has a range of potential applications.
Answerable or Not: Devising a Dataset for Extending Machine Reading Comprehension
However, to realize human-like language comprehension ability, a machine should also be able to distinguish not-answerable questions (NAQs) from answerable questions.
Classifying Lexical-semantic Relationships by Exploiting Sense/Concept Representations
This paper proposes a method for classifying the type of lexical-semantic relation between a given pair of words.
